Page 123

Contents | 123 of 173

Page 123

Download PDF | | Reference URL | Gallery View | Parent Record

Title	Neural network processing of oscillometric waveforms and blood pressure estimation from the superficial temporal artery
Publication Type	dissertation
School or College	College of Engineering
Department	Bioengineering
Author	Baker, Phillip Donald
Date	1990
Description	The objectives of this dissertation were: 1) to develop and evaluate neural networks for processing noninvasive oscillometric waveforms into estimates of blood pressure, 2) to construct an occlusive pad for recording oscillometric waveforms from the superficial temporal artery (STA) of the head, and 3) to evaluate the STA as a site for noninvasive estimation of blood pressure. Simultaneously recorded invasive blood pressure and noninvasive oscillometric waveforms from the forelimbs of five dogs (n = 425) were used to train and compare neural networks with conventional oscillometric algorithms. The intersubject mean differences and standard deviations of the differences between invasive and both noninvasive methods were similar (mean differences less than 5 mmHg and standard deviations of about 5 mmHg). However, average intrasubject standard deviations were consistently lower for neural networks (e.g., estimating mean blood pressure, 2.74 and 3.78 mmHg for neural networks and conventional algorithms, respectively). The neural networks were found to be less sensitive to noise and sparse data and thus provided a more robust and accurate method of estimating changes in a given subject's blood pressure. An occlusive pad for recording oscillometric waveforms from the STA was constructed and evaluated on 31 patients. Recordings were obtained from 20 of 21 thoracic intensive care unit (TICU) patients (n = 134) and 9 of 10 operating room (OR) patients (n = 94). Because of the limited amount of data available for training neural networks, oscillometric estimates were obtained with conventional arm oscillometric algorithms. TICU intersubject mean differences ± the standard deviations of the differences between invasive aortic measurements and STA oscillometric estimates of diastolic, mean, and systolic blood pressure were 4.69 ± 4.50, 14.36 ± 4.43, and 26.87 ± 7.93 mmHg, respectively. OR statistics comparing invasive radial artery measurements and noninvasive STA estimates were -2.80 ± 8.48, 4.58 ± 7.85, and 18.86 ± 8.78 mmHg, respectively. Although large, the differences between invasive aortic or radial artery measurements and noninvasive STA estimates were consistent over the range of blood pressures encountered. The standard deviations of the differences were similar to values reported in comparison studies of arm invasive and noninvasive methods. The expectation is that neural networks trained on STA oscillometric waveforms can compensate for the observed differences and thus provide reasonable estimates of central arterial blood pressure from the superficial temporal artery.
Type	Text
Publisher	University of Utah
Subject	blood pressure; measurement
Language	eng
Rights Management	© Phillip Donald Baker
Format	application/pdf
Format Medium	application/pdf
ARK	ark:/87278/s61x9phd
Setname	ir_etd
ID	2898814
Reference URL	https://collections.lib.utah.edu/ark:/87278/s61x9phd

Page Metadata

Title	Page 123
Format	application/pdf
Setname	ir_etd
ID	2898937
OCR Text	Show 112 beat-to-beat blood measurements the over noninvasive recording period. Results 5.2.2 half the approximately In artery blood pressure pad to the palpate secured with the notches guide as headband, for although patients, present, a an attempt an The pad was made to the pad 1 than aberrant nearly always recorded oscillometric mmHg or the course shape of the did not have the (i.e., shown in Figure 1.2 pad normally took no more and fall, in two was of the the was temporal artery ear repositioned if the maximum amplitude of waveform However, the the the oscillometric minutes. head and of less the was palpating the after was Repositioning of the other half signal improve waveform rise on Figure 3.3, using the In oscillometric characteristic in shown as positioned without having positioned oscillometric was was pad placement. signal by repositioning artery. successful was The artery. patients the superficial temporal or as three difficult to patients and palpate 10 than the and 4.3) . 15 or superficial repositioning was repeated several times. Noninvasive recordings were oscillometric had peak superficial temporal artery oscillometric waveforms of from all one 21 However, patients. of the patients, pulse amplitudes of less than 0.75 mmHg, difficult to process The from obtained recordings with the from this available patient were invasive and noninvasive methods. recordings were excluded, which distorted either the oscillometric waveform. because of not obvious 5.1 shows an software. the two comparison other noise and artifact, invasive blood pressure Figure female, which made them used in Similarly obese an and hardware the or noninvasive example of a
Reference URL	https://collections.lib.utah.edu/ark:/87278/s61x9phd/2898937